forked from srbhr/Resume-Matcher
-
Notifications
You must be signed in to change notification settings - Fork 0
/
streamlit_app.py
301 lines (231 loc) · 10.1 KB
/
streamlit_app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
import json
import os
from typing import List
import networkx as nx
import nltk
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import streamlit as st
from annotated_text import annotated_text, parameters
from streamlit_extras import add_vertical_space as avs
from streamlit_extras.badges import badge
from scripts.similarity import get_similarity_score, find_path, read_config
from scripts.utils import get_filenames_from_dir
cwd = find_path('Resume-Matcher')
config_path = os.path.join(cwd, "scripts", "similarity")
try:
nltk.data.find('tokenizers/punkt')
except LookupError:
nltk.download('punkt')
parameters.SHOW_LABEL_SEPARATOR = False
parameters.BORDER_RADIUS = 3
parameters.PADDING = "0.5 0.25rem"
def create_star_graph(nodes_and_weights, title):
# Create an empty graph
G = nx.Graph()
# Add the central node
central_node = "resume"
G.add_node(central_node)
# Add nodes and edges with weights to the graph
for node, weight in nodes_and_weights:
G.add_node(node)
G.add_edge(central_node, node, weight=weight * 100)
# Get position layout for nodes
pos = nx.spring_layout(G)
# Create edge trace
edge_x = []
edge_y = []
for edge in G.edges():
x0, y0 = pos[edge[0]]
x1, y1 = pos[edge[1]]
edge_x.extend([x0, x1, None])
edge_y.extend([y0, y1, None])
edge_trace = go.Scatter(x=edge_x, y=edge_y, line=dict(
width=0.5, color='#888'), hoverinfo='none', mode='lines')
# Create node trace
node_x = []
node_y = []
for node in G.nodes():
x, y = pos[node]
node_x.append(x)
node_y.append(y)
node_trace = go.Scatter(x=node_x, y=node_y, mode='markers', hoverinfo='text',
marker=dict(showscale=True, colorscale='Rainbow', reversescale=True, color=[], size=10,
colorbar=dict(thickness=15, title='Node Connections', xanchor='left',
titleside='right'), line_width=2))
# Color node points by number of connections
node_adjacencies = []
node_text = []
for node in G.nodes():
adjacencies = list(G.adj[node]) # changes here
node_adjacencies.append(len(adjacencies))
node_text.append(f'{node}<br># of connections: {len(adjacencies)}')
node_trace.marker.color = node_adjacencies
node_trace.text = node_text
# Create the figure
fig = go.Figure(data=[edge_trace, node_trace],
layout=go.Layout(title=title, titlefont_size=16, showlegend=False,
hovermode='closest', margin=dict(b=20, l=5, r=5, t=40),
xaxis=dict(
showgrid=False, zeroline=False, showticklabels=False),
yaxis=dict(showgrid=False, zeroline=False, showticklabels=False)))
# Show the figure
st.plotly_chart(fig)
def create_annotated_text(input_string: str, word_list: List[str], annotation: str, color_code: str):
# Tokenize the input string
tokens = nltk.word_tokenize(input_string)
# Convert the list to a set for quick lookups
word_set = set(word_list)
# Initialize an empty list to hold the annotated text
annotated_text = []
for token in tokens:
# Check if the token is in the set
if token in word_set:
# If it is, append a tuple with the token, annotation, and color code
annotated_text.append((token, annotation, color_code))
else:
# If it's not, just append the token as a string
annotated_text.append(token)
return annotated_text
def read_json(filename):
with open(filename) as f:
data = json.load(f)
return data
def tokenize_string(input_string):
tokens = nltk.word_tokenize(input_string)
return tokens
st.image('Assets/img/header_image.jpg')
st.title(':blue[Resume Matcher]')
st.subheader(
'Free and Open Source ATS to help your resume pass the screening stage.')
st.markdown(
"Check the website [www.resumematcher.fyi](https://www.resumematcher.fyi/)")
st.markdown(
'⭐ Give Resume Matcher a Star on [GitHub](https://github.com/srbhr/resume-matcher)')
badge(type="github", name="srbhr/Resume-Matcher")
st.text('For updates follow me on Twitter.')
badge(type="twitter", name="_srbhr_")
st.markdown(
'If you like the project and would like to further help in development please consider 👇')
badge(type="buymeacoffee", name="srbhr")
avs.add_vertical_space(5)
resume_names = get_filenames_from_dir("Data/Processed/Resumes")
output = 0
if len(resume_names) > 1:
st.write("There are", len(resume_names),
" resumes present. Please select one from the menu below:")
output = st.slider('Select Resume Number', 0, len(resume_names) - 1, 0)
else:
st.write("There is 1 resume present")
avs.add_vertical_space(5)
st.write("You have selected ", resume_names[output], " printing the resume")
selected_file = read_json("Data/Processed/Resumes/" + resume_names[output])
avs.add_vertical_space(2)
st.markdown("#### Parsed Resume Data")
st.caption(
"This text is parsed from your resume. This is how it'll look like after getting parsed by an ATS.")
st.caption("Utilize this to understand how to make your resume ATS friendly.")
avs.add_vertical_space(3)
# st.json(selected_file)
st.write(selected_file["clean_data"])
avs.add_vertical_space(3)
st.write("Now let's take a look at the extracted keywords from the resume.")
annotated_text(create_annotated_text(
selected_file["clean_data"], selected_file["extracted_keywords"],
"KW", "#0B666A"))
avs.add_vertical_space(5)
st.write("Now let's take a look at the extracted entities from the resume.")
# Call the function with your data
create_star_graph(selected_file['keyterms'], "Entities from Resume")
df2 = pd.DataFrame(selected_file['keyterms'], columns=["keyword", "value"])
# Create the dictionary
keyword_dict = {}
for keyword, value in selected_file['keyterms']:
keyword_dict[keyword] = value * 100
fig = go.Figure(data=[go.Table(header=dict(values=["Keyword", "Value"],
font=dict(size=12),
fill_color='#070A52'),
cells=dict(values=[list(keyword_dict.keys()),
list(keyword_dict.values())],
line_color='darkslategray',
fill_color='#6DA9E4'))
])
st.plotly_chart(fig)
st.divider()
fig = px.treemap(df2, path=['keyword'], values='value',
color_continuous_scale='Rainbow',
title='Key Terms/Topics Extracted from your Resume')
st.write(fig)
avs.add_vertical_space(5)
job_descriptions = get_filenames_from_dir("Data/Processed/JobDescription")
output = 0
if len(job_descriptions) > 1:
st.write("There are", len(job_descriptions),
" job descriptions present. Please select one from the menu below:")
output = st.slider('Select Job Description Number',
0, len(job_descriptions) - 1, 0)
else:
st.write("There is 1 job description present")
avs.add_vertical_space(5)
st.write("You have selected ",
job_descriptions[output], " printing the job description")
selected_jd = read_json(
"Data/Processed/JobDescription/" + job_descriptions[output])
avs.add_vertical_space(2)
st.markdown("#### Job Description")
st.caption(
"Currently in the pipeline I'm parsing this from PDF but it'll be from txt or copy paste.")
avs.add_vertical_space(3)
# st.json(selected_file)
st.write(selected_jd["clean_data"])
st.markdown("#### Common Words between Job Description and Resumes Highlighted.")
annotated_text(create_annotated_text(
selected_file["clean_data"], selected_jd["extracted_keywords"],
"JD", "#F24C3D"))
st.write("Now let's take a look at the extracted entities from the job description.")
# Call the function with your data
create_star_graph(selected_jd['keyterms'], "Entities from Job Description")
df2 = pd.DataFrame(selected_jd['keyterms'], columns=["keyword", "value"])
# Create the dictionary
keyword_dict = {}
for keyword, value in selected_jd['keyterms']:
keyword_dict[keyword] = value * 100
fig = go.Figure(data=[go.Table(header=dict(values=["Keyword", "Value"],
font=dict(size=12),
fill_color='#070A52'),
cells=dict(values=[list(keyword_dict.keys()),
list(keyword_dict.values())],
line_color='darkslategray',
fill_color='#6DA9E4'))
])
st.plotly_chart(fig)
st.divider()
fig = px.treemap(df2, path=['keyword'], values='value',
color_continuous_scale='Rainbow',
title='Key Terms/Topics Extracted from the selected Job Description')
st.write(fig)
avs.add_vertical_space(3)
config_file_path = config_path + "/config.yml"
if os.path.exists(config_file_path):
config_data = read_config(config_file_path)
if config_data:
print("Config file parsed successfully:")
resume_string = ' '.join(selected_file["extracted_keywords"])
jd_string = ' '.join(selected_jd["extracted_keywords"])
result = get_similarity_score(resume_string, jd_string)
similarity_score = result[0]["score"]
st.write("Similarity Score obtained for the resume and job description is:", similarity_score)
else:
print("Config file does not exist.")
st.title(':blue[Resume Matcher]')
st.subheader(
'Free and Open Source ATS to help your resume pass the screening stage.')
st.markdown(
'⭐ Give Resume Matcher a Star on [GitHub](https://github.com/srbhr/Resume-Matcher/)')
badge(type="github", name="srbhr/Resume-Matcher")
st.text('For updates follow me on Twitter.')
badge(type="twitter", name="_srbhr_")
st.markdown(
'If you like the project and would like to further help in development please consider 👇')
badge(type="buymeacoffee", name="srbhr")